Voice Remixing quickstart

This guide shows you how to remix an existing voice to create a new one.

Using the Voice Design API

This guide assumes you have set up your API key and SDK. Complete the quickstart first if you haven’t. To play audio through your speakers, you may also need MPV and/or ffmpeg.

Make the API request

Remixing a voice is a two step process:

Generate a preview of the new voice by providing a voice ID and a prompt.
Create the new voice from the preview.

We’ll start by generating a preview of the new voice.

Create a new file named example.py or example.mts, depending on your language of choice and add the following code:

You can only remix previously designed voices, IVC or PVC voices, and any voices from the Voice Library that have infinite notice periods.

1 # example.py
2 from dotenv import load_dotenv
3 from elevenlabs.client import ElevenLabs
4 from elevenlabs.play import play
5 import base64
6 
7 load_dotenv()
8 
9 elevenlabs = ElevenLabs(
10     api_key=os.getenv("ELEVENLABS_API_KEY"),
11 )
12 
13 voices = elevenlabs.text_to_voice.remix(
14     voice_id="JBFqnCBsd6RMkjVDRZzb"
15     voice_description="Use a higher pitch and change to a Boston accent.",
16     text="Of course I'm a Bostonian, I've lived here all my life!",
17 )
18 
19 for preview in voices.previews:
20     # Convert base64 to audio buffer
21     audio_buffer = base64.b64decode(preview.audio_base_64)
22 
23     print(f"Playing preview: {preview.generated_voice_id}")
24 
25     play(audio_buffer)

Execute the code

1 python example.py

You should hear the generated voice previews playing through your speakers, one at a time.

Add generated voice to your library

Once you’ve generated the previews and picked your favorite, you can add it to your voice library via the generated voice ID so it can be used with other APIs.

1 voice = elevenlabs.text_to_voice.create(
2     voice_name="Bostonian",
3     voice_description="A high pitched Bostonian accent.",
4     # The generated voice ID of the preview you want to use,
5     # using the first in the list for this example
6     generated_voice_id=voices.previews[0].generated_voice_id
7 )
8 
9 print(voice.voice_id)

Using the Voice Design API

This guide assumes you have set up your API key and SDK. Complete the quickstart first if you haven’t. To play audio through your speakers, you may also need MPV and/or ffmpeg.

Make the API request

Remixing a voice is a two step process:

Generate a preview of the new voice by providing a voice ID and a prompt.
Create the new voice from the preview.

We’ll start by generating a preview of the new voice.

Create a new file named example.py or example.mts, depending on your language of choice and add the following code:

You can only remix previously designed voices, IVC or PVC voices, and any voices from the Voice Library that have infinite notice periods.

1 # example.py
2 from dotenv import load_dotenv
3 from elevenlabs.client import ElevenLabs
4 from elevenlabs.play import play
5 import base64
6 
7 load_dotenv()
8 
9 elevenlabs = ElevenLabs(
10     api_key=os.getenv("ELEVENLABS_API_KEY"),
11 )
12 
13 voices = elevenlabs.text_to_voice.remix(
14     voice_id="JBFqnCBsd6RMkjVDRZzb"
15     voice_description="Use a higher pitch and change to a Boston accent.",
16     text="Of course I'm a Bostonian, I've lived here all my life!",
17 )
18 
19 for preview in voices.previews:
20     # Convert base64 to audio buffer
21     audio_buffer = base64.b64decode(preview.audio_base_64)
22 
23     print(f"Playing preview: {preview.generated_voice_id}")
24 
25     play(audio_buffer)

Execute the code

1 python example.py

You should hear the generated voice previews playing through your speakers, one at a time.

Add generated voice to your library

Once you’ve generated the previews and picked your favorite, you can add it to your voice library via the generated voice ID so it can be used with other APIs.

1 voice = elevenlabs.text_to_voice.create(
2     voice_name="Bostonian",
3     voice_description="A high pitched Bostonian accent.",
4     # The generated voice ID of the preview you want to use,
5     # using the first in the list for this example
6     generated_voice_id=voices.previews[0].generated_voice_id
7 )
8 
9 print(voice.voice_id)

Voice Remixing quickstart

Voice Remixing quickstart

Using the Voice Design API

Make the API request

Execute the code

Add generated voice to your library

Next steps

Using the Voice Design API

Make the API request

Execute the code

Add generated voice to your library

Next steps

1	# example.py
2	from dotenv import load_dotenv
3	from elevenlabs.client import ElevenLabs
4	from elevenlabs.play import play
5	import base64
6
7	load_dotenv()
8
9	elevenlabs = ElevenLabs(
10	api_key=os.getenv("ELEVENLABS_API_KEY"),
11	)
12
13	voices = elevenlabs.text_to_voice.remix(
14	voice_id="JBFqnCBsd6RMkjVDRZzb"
15	voice_description="Use a higher pitch and change to a Boston accent.",
16	text="Of course I'm a Bostonian, I've lived here all my life!",
17	)
18
19	for preview in voices.previews:
20	# Convert base64 to audio buffer
21	audio_buffer = base64.b64decode(preview.audio_base_64)
22
23	print(f"Playing preview: {preview.generated_voice_id}")
24
25	play(audio_buffer)

1	voice = elevenlabs.text_to_voice.create(
2	voice_name="Bostonian",
3	voice_description="A high pitched Bostonian accent.",
4	# The generated voice ID of the preview you want to use,
5	# using the first in the list for this example
6	generated_voice_id=voices.previews[0].generated_voice_id
7	)
8
9	print(voice.voice_id)